© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 212166
    Prev
    Next
    INDEX
    Explanations

    offering of, to take, a relative, country ., smoking cigarettes, first time, attempt ., member brokers

    np_acts-logits-general · gemini-2.5-flash-lite

    want, choose, or directly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     着
    0.55
     വിഷ
    0.55
     シル
    0.54
    piej
    0.54
     まま
    0.54
     Při
    0.54
     ละ
    0.53
     ハン
    0.53
     ಒಳ್ಳೆಯ
    0.52
     ವಿಷ
    0.52
    POSITIVE LOGITS
     quatre
    0.46
     racked
    0.46
    دو
    0.45
     there
    0.44
     bottles
    0.43
    誦
    0.41
     superscript
    0.40
     varieties
    0.39
     mockup
    0.39
     tions
    0.39
    Activations Density 0.001%

    No Known Activations